About Bigquery Evals
Bigquery Evals is an MCP server in the Scraping category: read-only BigQuery MCP server with mandatory dry-run cost caps, agent-friendly structured errors, and a Spider/BIRD-style NL-to-SQL eval harness.
Install
git clone https://github.com/Umarfarook1/mcp-bigquery-evalsThis server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.
Tools (7)
describe_table(table_id)Schema, row count, size
Parameters not published.
estimate_cost(sql)Free dry-run; returns bytes_scanned and estimated USD
Parameters not published.
list_datasets()List all datasets in your GCP project
Parameters not published.
list_tables(dataset_id)List tables in a dataset
Parameters not published.
run_query(sql, max_bytes_scanned=100MB)Refuse non-`SELECT`, dry-run, refuse if over cap, then execute
Parameters not published.
sample_table(table_id, n=5)Up to n sample rows
Parameters not published.
search_schema(term)Fuzzy-match a term against all column names
Parameters not published.
Ask AI
Ask AI about Bigquery Evals
Powered by Claude · Grounded in docs
Security checks
6 checks have not been run yet.